W-Net: Two-Stage U-Net With Misaligned Data for Raw-to-RGB Mapping

  title={W-Net: Two-Stage U-Net With Misaligned Data for Raw-to-RGB Mapping},
  author={Kwang-Hyun Uhm and Seung-Wook Kim and Seo-Won Ji and Sung-Jin Cho and Jun Pyo Hong and S. Ko},
  journal={2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)},
  • Kwang-Hyun Uhm, Seung-Wook Kim, +3 authors S. Ko
  • Published 2019
  • Engineering, Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Recent research on a learning mapping between raw Bayer images and RGB images has progressed with the development of deep convolutional neural network. A challenging data set namely the Zurich Raw-to-RGB data set (ZRR) has been released in the AIM 2019 raw-to-RGB mapping challenge. In ZRR, input raw and target RGB images are captured by two different cameras and thus not perfectly aligned. Moreover, camera metadata such as white balance gains and color correction matrix are not provided, which… Expand
PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing
The model enhances PyNET, a recently proposed state-of-the-art model for mobile ISP, and improves its performance with channel attention and subpixel reconstruction module, and demonstrates the performance of the proposed method with comparative experiments and results from the AIM 2020 learned smartphone ISP challenge. Expand
AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results
This paper reviews the first AIM challenge on mapping camera RAW toRGB images with the focus on proposed solutions and results, defining the state-of-the-art for RAW to RGB image restoration. Expand
AWNet: Attentive Wavelet Network for Image ISP
A novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem, and enables us to restore favorable image details from RAW information and achieve a larger receptive field while remaining high efficiency in terms of computational cost. Expand
Robust white balance estimation using joint attention and angular loss optimization
White balance estimation (WBE) is one of the most fundamental and crucial steps in modern Image Signal Processor (ISP). Recent years have witnessed the advancements of deep-learning based WBE.Expand
In-Camera Raw Compression: A New Paradigm from Image Acquisition to Display
  • Zhihao Li, Haojie Liu, Lin Yang, Zhan Ma
  • Computer Science
  • 2020 54th Asilomar Conference on Signals, Systems, and Computers
  • 2020
The NeuralCAM is proposed- a new camera processing paradigm where the sensor raw Bayer data is compressed and the image signal processor is applied at users’ client for on-demand rendering and processing. Expand
C3Net: Demoiréing Network Attentive in Channel, Color and Concatenation
The proposed C3Net showed state-of-the-art results in the benchmark dataset on NTIRE 2020 demoiréing challenge by transferring multi-scale information by concatenation, not multiplying with the insignificant weights by sigmoid function. Expand
O-Net: Dangerous Goods Detection in Aviation Security Based on U-Net
The comparative analysis of basic segmentation models such as Fully Convolutional Networks, U-Net, and Segmentation-networks based on the major performance indicators of segmentation-pixel accuracy and mean-intersection over union revealed that O-Net improved the average pixel accuracy by 5.8%, 2.26%, and 5.01% and the m-IoU was improved by 43.1%, 9.84%, and 23.31%, respectively. Expand


DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
An end-to-end deep learning approach that bridges the gap by translating ordinary photos into DSLR-quality images by learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness. Expand
MSR-net: Low-light Image Enhancement Using Deep Convolutional Network
A Convolutional Neural Network (MSR-net) that directly learns an end-to-end mapping between dark and bright images and shows that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Expand
DeepISP: Toward Learning an End-to-End Image Processing Pipeline
The proposed solution achieves the state-of-the-art performance in objective evaluation of peak signal-to-noise ratio on the subtask of joint denoising and demosaicing and achieves better visual quality compared to the manufacturer ISP. Expand
AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results
This paper reviews the first AIM challenge on mapping camera RAW toRGB images with the focus on proposed solutions and results, defining the state-of-the-art for RAW to RGB image restoration. Expand
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time. Expand
Learning to See in the Dark
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. Expand
Deep joint demosaicking and denoising
A new data-driven approach forDemosaicking and denoising is introduced: a deep neural network is trained on a large corpus of images instead of using hand-tuned filters and this network and training procedure outperform state-of-the-art both on noisy and noise-free data. Expand
Raw-to-Raw: Mapping between Image Sensor Color Responses
An illumination-independent mapping approach that uses white-balancing to assist in reducing the number of required transformations is introduced that achieves state-of-the-art results on a range of consumer cameras and images of arbitrary scenes and illuminations. Expand
Toward Convolutional Blind Denoising of Real Photographs
A convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs and a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand